Skip to content

Glossary: Deep Learning Basics

Transform

Also written: transforms, v2.Compose, ToImage, ToDtype, transforms.v2

A function applied to each example as it's loaded. In `torchvision.transforms.v2`, `ToImage` makes an image tensor, `ToDtype(torch.float32, scale=True)` scales 0 to 255 into 0 to 1, and `Compose` chains them.

Where the book teaches it

Related terms

torchvisionFashionMNIST